The Economist / robots.txt snapshot
← back to economist.com · fetched 2026-07-17T12:07:56Z (19d ago) · HTTP 200 · 2063 bytes · sha256 b2ece64380719e0c · raw
final URL: https://www.economist.com/robots.txt
| 1 | # robots.txt |
| 2 | |
| 3 | # Sitemaps |
| 4 | |
| 5 | Sitemap: https://www.economist.com/sitemap.xml |
| 6 | Sitemap: https://www.economist.com/googlenews.xml |
| 7 | |
| 8 | # ========================================== |
| 9 | # USER-FACING LLM BOTS |
| 10 | # Allowed to fetch /pro/ on behalf of a user |
| 11 | # ========================================== |
| 12 | |
| 13 | User-agent: ChatGPT-User |
| 14 | Allow: /pro/ |
| 15 | Disallow: / |
| 16 | |
| 17 | User-agent: Claude-Web |
| 18 | Allow: /pro/ |
| 19 | Disallow: / |
| 20 | |
| 21 | User-agent: PerplexityBot |
| 22 | Allow: /pro/ |
| 23 | Disallow: / |
| 24 | |
| 25 | User-agent: Perplexity-User |
| 26 | Allow: /pro/ |
| 27 | Disallow: / |
| 28 | |
| 29 | # I have added OAI-SearchBot (OpenAI's live search agent) |
| 30 | # as it behaves the same way as ChatGPT-User. |
| 31 | User-agent: OAI-SearchBot |
| 32 | Allow: /pro/ |
| 33 | Disallow: / |
| 34 | |
| 35 | # ========================================== |
| 36 | # TRAINING BOTS & MASS SCRAPERS |
| 37 | # Completely blocked from the entire site |
| 38 | # ========================================== |
| 39 | |
| 40 | User-agent: GPTBot |
| 41 | Disallow: / |
| 42 | |
| 43 | # Google-Extended is used by the Gemini app for searches on |
| 44 | # behalf of the user but it also used for training |
| 45 | User-agent: Google-Extended |
| 46 | Disallow: / |
| 47 | |
| 48 | User-agent: anthropic-ai |
| 49 | Disallow: / |
| 50 | |
| 51 | User-agent: Applebot-Extended |
| 52 | Disallow: / |
| 53 | |
| 54 | User-Agent: Bytespider |
| 55 | Disallow: / |
| 56 | |
| 57 | User-agent: CCBot |
| 58 | Disallow: / |
| 59 | |
| 60 | # ========================================== |
| 61 | # OTHER MISCELLANEOUS BOTS |
| 62 | # Completely blocked |
| 63 | # ========================================== |
| 64 | |
| 65 | User-agent: PiplBot |
| 66 | Disallow: / |
| 67 | |
| 68 | User-agent: TurnitinBot |
| 69 | Disallow: / |
| 70 | |
| 71 | User-agent: PetalBot |
| 72 | Disallow: / |
| 73 | |
| 74 | User-agent: MoodleBot |
| 75 | Disallow: / |
| 76 | |
| 77 | User-agent: magpie-crawler |
| 78 | Disallow: / |
| 79 | |
| 80 | User-agent: ia_archiver |
| 81 | Disallow: / |
| 82 | |
| 83 | User-Agent: Mozilla/5.0 (compatible; parse.ly scraper/0.16; +http://parsely.com) |
| 84 | Disallow: /checkout |
| 85 | |
| 86 | # ========================================== |
| 87 | # GENERAL CRAWLERS (e.g., Googlebot, Bingbot) |
| 88 | # Allowed by default, but blocked from select paths |
| 89 | # ========================================== |
| 90 | User-agent: * |
| 91 | Disallow: /5605/ |
| 92 | Disallow: /pubads.g.doubleclick.net/ |
| 93 | Disallow: /assets/infographic/ |
| 94 | Disallow: /search/ |
| 95 | Disallow: /search?q= |
| 96 | Disallow: /graphql |
| 97 | Disallow: /subscribe/getstarted/ |
| 98 | Disallow: /checkout |
| 99 | Disallow: /switch* |
| 100 | Disallow: /audio-edition-podcast/*/index.xml |